Deep Learning in Theory and PracticeHU0F0SHPHPHP-HU0F0S1.0<h5>At the end of this course, you will be able to: </h5><ul>
<li>Design and develop neural network models in structured frameworks</li><li>Understand core buzzwords and terminology</li><li>Kick-start a deep learning project</li><li>Build a suitable deep learning model for a given problem statement</li><li>Export the deep learning model for consumption by other app developers</li></ul><ul>
<li>Basic understanding of any programming or scripting language</li></ul><ul>
<li>This course is ideal for data engineers, data scientists, researchers, solution architects, software engineers, AI enthusiasts, statisticians and other IT professionals looking for a practical foundation in deep learning with neural networks.</li></ul><h5>Module 1 A Gentle Introduction to Deep Learning </h5><ul>
<li>History of deep learning • Ethics in AI</li><li>Overview of deep learning</li><li>A single neuron</li><li>What is a transfer function?</li></ul><h5>Module 2 Introduction to TensorFlow </h5><ul>
<li>Introduction to TensorFlow</li><li>The TensorFlow architecture</li><li>TensorFlow data</li></ul><h5>Module 3 Introduction to Keras </h5><ul>
<li>Introduction to Keras</li><li>The Keras architecture</li><li>Keras models</li><li>Keras sequential vs functional API</li><li>Keras layers</li><li>Keras core modules</li></ul><h5>Module 4 Overfitting and Underfitting </h5><ul>
<li>Overfitting and underfitting</li><li>How to avoid</li></ul>
<h5>Module 5 Activation, Loss and Optimizer Functions </h5><ul>
<li>Activation functions</li><li>Loss functions</li><li>Optimization functions</li></ul><h5>Module 6 Regularizing a Model & Hyperparameter Optimization </h5><ul>
<li>Why regularize?</li><li>Regularization types</li><li>Hyperparameters</li><li>Optimization techniques</li></ul><h5>Module 7 Pooling and Convolutions </h5><ul>
<li>Convolutions</li><li>Pooling in neural networks</li></ul><h5>Module 8 Big Data Deep Learning </h5><ul>
<li>The big data perspective</li><li>The big data deep learning team and roles</li><li>Apache Spark</li><li>Databricks</li><li>Determined AI</li><li>HPE Ezmeral</li></ul>At the end of this course, you will be able to:
- Design and develop neural network models in structured frameworks
- Understand core buzzwords and terminology
- Kick-start a deep learning project
- Build a suitable deep learning model for a given problem statement
- Export the deep learning model for consumption by other app developers- Basic understanding of any programming or scripting language- This course is ideal for data engineers, data scientists, researchers, solution architects, software engineers, AI enthusiasts, statisticians and other IT professionals looking for a practical foundation in deep learning with neural networks.Module 1 A Gentle Introduction to Deep Learning
- History of deep learning • Ethics in AI
- Overview of deep learning
- A single neuron
- What is a transfer function?
Module 2 Introduction to TensorFlow
- Introduction to TensorFlow
- The TensorFlow architecture
- TensorFlow data
Module 3 Introduction to Keras
- Introduction to Keras
- The Keras architecture
- Keras models
- Keras sequential vs functional API
- Keras layers
- Keras core modules
Module 4 Overfitting and Underfitting
- Overfitting and underfitting
- How to avoid
Module 5 Activation, Loss and Optimizer Functions
- Activation functions
- Loss functions
- Optimization functions
Module 6 Regularizing a Model & Hyperparameter Optimization
- Why regularize?
- Regularization types
- Hyperparameters
- Optimization techniques
Module 7 Pooling and Convolutions
- Convolutions
- Pooling in neural networks
Module 8 Big Data Deep Learning
- The big data perspective
- The big data deep learning team and roles
- Apache Spark
- Databricks
- Determined AI
- HPE Ezmeral2 jours1800.001500.001500.00